Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 23460
    Prev
    Next
    INDEX
    Explanations

    references to physical stretching or extension

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physical stretching and extension

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.87
    nect
    -0.82
    osal
    -0.82
    mine
    -0.80
    ership
    -0.79
    vals
    -0.76
    lies
    -0.75
    eer
    -0.74
    abad
    -0.73
    eers
    -0.73
    POSITIVE LOGITS
     stretched
    1.12
     stretching
    1.09
     stretches
    0.92
     tremend
    0.80
     stretch
    0.76
     horizont
    0.75
     Afric
    0.73
    Stretch
    0.72
    ĸļ
    0.70
    OPLE
    0.68
    Activations Density 0.008%

    No Known Activations